INDEX
    Explanations

    mentions of religious institutions, particularly churches

    New Auto-Interp
    Negative Logits
    eec
    -0.15
    aks
    -0.15
    ernaut
    -0.15
    ode
    -0.14
    emale
    -0.14
    aries
    -0.14
     Oaks
    -0.14
     crack
    -0.14
    ãĥ¼ãĥĦ
    -0.14
    ated
    -0.14
    POSITIVE LOGITS
    yard
    0.29
    going
    0.20
    illon
    0.19
    (es
    0.19
    yards
    0.19
    wide
    0.19
    ouse
    0.18
    ill
    0.18
    go
    0.17
    elijke
    0.17
    Act Density 0.023%

    No Known Activations